CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Human activity prediction using temporally-weighted generalized time warping
Wang, Haoran1; Yang, Wankou2; Yuan, Chunfeng3; Ling, Haibin4; Hu, Weiming3
Source PublicationNEUROCOMPUTING
AbstractDifferent from traditional human activity recognition, human activity prediction aims to recognize an unfinished activity, typically in absence of explicit temporal progress status. In this paper, we propose a new human activity prediction approach by extending the recently proposed generalized time warping (GTW) [20], which allows an efficient and flexible alignment of two or more multi-dimensional time series. More specifically, for each activity video, either complete or incomplete, we first decompose it into a sequence of short video segments. Then, we represent each segment by the local spatial-temporal statistics using the classical bag-of visual -words model. In this way, the comparison between a query sequence (i.e., containing an incomplete activity) and a reference sequence (i.e., containing a full activity) boils down to the problem of aligning their corresponding segment sequences. While GTW treats different portions of a sequence as equally important, our task is in favor of early portions since an incomplete activity video always aligns from the beginning of a complete one. Thus motivated, we develop a temporally-weighted GTW (TGTW) algorithm for the activity prediction problem by encouraging alignment in the early portion of an activity sequence. Finally, the similarity derived from TGTW is combined with the k-nearest neighbors algorithm for predicting the activity class of an input sequence. The proposed approach is evaluated on several publicly available datasets in comparison with state-of-the-art approaches. The experimental results and analysis clearly demonstrate the effectiveness of the proposed approach.
KeywordActivity Prediction Time Warping Alignment
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationNational Natural Science Foundation of China(61603080 ; Fundamental Research Funds for the Central Universities of China(N150403006) ; NSF of Jiangsu Province(BK20140566 ; China Postdoctoral science Foundation(2014M561586) ; 61473086 ; BK20150470) ; 61375001)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000392164400014
Citation statistics
Document Type期刊论文
Affiliation1.Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Peoples R China
2.Southeast Univ, Sch Automat, Nanjing 210096, Jiangsu, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
4.Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 USA
Recommended Citation
GB/T 7714
Wang, Haoran,Yang, Wankou,Yuan, Chunfeng,et al. Human activity prediction using temporally-weighted generalized time warping[J]. NEUROCOMPUTING,2017,225(1):139-147.
APA Wang, Haoran,Yang, Wankou,Yuan, Chunfeng,Ling, Haibin,&Hu, Weiming.(2017).Human activity prediction using temporally-weighted generalized time warping.NEUROCOMPUTING,225(1),139-147.
MLA Wang, Haoran,et al."Human activity prediction using temporally-weighted generalized time warping".NEUROCOMPUTING 225.1(2017):139-147.
Files in This Item: Download All
File Name/Size DocType Version Access License
wanghaoran-Human act(1309KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Haoran]'s Articles
[Yang, Wankou]'s Articles
[Yuan, Chunfeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Haoran]'s Articles
[Yang, Wankou]'s Articles
[Yuan, Chunfeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Haoran]'s Articles
[Yang, Wankou]'s Articles
[Yuan, Chunfeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: wanghaoran-Human activity prediction using temporally-weighted generalized time warping.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.